Senior Agentic AI & LLM Engineer

Job Summary

This role involves leading the design, development, and deployment of production-grade agentic AI and LLM systems for enterprise clients in Saudi Arabia, managing multi-agent architectures and LLM integrations from architecture to live deployment.

Responsibilities

• Develop and maintain production data pipelines for LLM ingestion, embedding generation, and retrieval workflows.
• Design vector store architectures and manage embedding pipelines for structured and unstructured enterprise data.
• Manage cloud AI infrastructure on Azure or AWS, including model hosting, API gateway, and cost optimization.
• Ensure data quality, lineage, and governance standards for AI deployments in regulated environments.
• Define observability standards such as logging, tracing, drift detection, and cost monitoring for AI systems in production.
• Build and maintain AI orchestration pipelines covering data ingestion, model inference, and result delivery.
• Design and operate RAG pipelines with vector databases for enterprise knowledge retrieval.
• Integrate LLMs with external tools and APIs to create autonomous multi-step agentic workflows.

Must haves

• Proficiency in Python (primary), SQL (advanced), and PySpark.
• Experience with AI/ML frameworks including PyTorch, Scikit-learn, Hugging Face Transformers, LangChain, and LangGraph.
• Familiarity with agentic frameworks such as LangGraph, AutoGen, CrewAI, or similar multi-agent orchestration tools.
• Experience with data tooling like dbt, PySpark, Airflow, Kafka, or Flink.
• Cloud experience with Azure (preferred), AWS, or GCP.
• At least 6 years of hands-on experience delivering production AI or data systems, not proofs of concept or academic projects.
• Hands-on experience with LLMs including prompt engineering, fine-tuning, RAG, and model compression.
• Experience taking at least one agentic AI system from design through to production.
• Knowledge of AI model risk frameworks and audit trail requirements.
• Fluent English (written and spoken) and currently based in Saudi Arabia with a valid, transferable Iqama.
• Proficiency in Agile/Scrum and ability to self-manage sprint commitments.

Nice to haves

• Familiarity with Saudi data and AI governance frameworks, NCA requirements, or PDPL compliance.
• Experience with MLflow or similar tools for experiment tracking and model registry.

We refresh listings regularly, but some roles close early on the source platform.